Yongbin Gao
Papers
6
Total Citations
83
H-Index
4
About
Yongbin Gao is a leading researcher in 3D computer vision, with a focus on depth estimation, multi-modal perception, and autonomous systems. His work addresses critical challenges in enabling intelligent agents—from robots to autonomous vehicles—to perceive and interact with 3D environments without relying on expensive sensors like LiDAR. Gao’s most cited paper, "Multi-modal 3D object detection by 2D-guided precision anchor proposal and multi-layer fusion" (2021, 38 citations), introduces a novel framework that fuses 2D and 3D data for robust object detection. He has also made significant contributions to self-supervised learning, as demonstrated in "Self-Supervised Learning of Depth and Ego-Motion for 3D Perception in Human Computer Interaction" (2023, 10 citations), which reduces dependency on costly hardware. His work on "Depth Estimation of Video Sequences With Perceptual Losses" (2018, 24 citations) pioneered unsupervised depth recovery using perceptual losses, advancing monocular 3D reconstruction. More recently, Gao has explored diffusion models for multi-modal crack segmentation (2024) and global fusion frameworks for depth estimation (2025), pushing the boundaries of robust perception in real-world, noisy environments. With over 80 total citations, his research continues to shape the future of affordable, scalable 3D perception.
Research Focus
Key Achievements
Top Papers
- 1
- 2Depth Estimation of Video Sequences With Perceptual Losses24 citations · 2018
- 3
- 4
- 5
- 6Multi-modal Scene Global Fusion Framework for Enhanced Depth Estimation1 citations · 2025